检索结果-内蒙古大学图书馆

Bayesian adaptive estimation: The next dimension

JOURNAL OF MATHEMATICAL PSYCHOLOGY 2006年第4期50卷 369-389页

作者： Kujala, JV Lukka, TJ Univ Jyvaskyla Agora Ctr FI-40014 Jyvaskyla Finland Hybrid Graph FI-00130 Helsinki Finland

We propose a new psychometric model for two-dimensional stimuli, such as color differences, based on parameterizing the threshold of a one-dimensional psychometric function as ail ellipse. The P Bayesian adaptive estimation method applied to this model yields trials that vary in multiple stimulus dimensions simultaneously. Simulations indicate that this new procedure can be much more efficient than the more conventional procedure of estimating the psychometric function on one-dimensional lines independently, requiring only one-fourth or less the number of trials for equivalent performance in typical situations. In a real psychophysical experiment with a yes-no task, as few as 22 trials per estimated threshold ellipse were enough to consistently demonstrate certain color appearance phenomena. We discuss the practical implications of the multidimensional adaptation. In order to make the application of the model practical, we present two significantly faster algorithms for running the P method: a discretized algorithm utilizing the Fast Fourier Transform for better scaling with the sampling rates and a Monte Carlo particle filter algorithm that should be able to scale into even more dimensions. (c) 2006 Elsevier Inc. All rights reserved.

关键词： Bayesian adaptive method psychometric function two-dimensional stimuli fast Fourier transform particle filter algorithm Markov chain Monte Carlo

来源：评论

学校读者我要写书评

暂无评论

Flood Routing Model with particle filter-Based Data Assimilation for Flash Flood Forecasting in the Micro-Model of Lower Yellow River, China

引用

WATER 2018年第11期10卷 1612页

作者： Chen, Minghong Pang, Juanjuan Wu, Pengxiang China Agr Univ Coll Water Resources & Civil Engn Beijing 100083 Peoples R China

Reliable real-time flood forecasting is a challenging prerequisite for successful flood protection. This study developed a flood routing model combined with a particle filter-based assimilation model and a one-dimensional hydrodynamic model. This model was applied to an indoor micro-model, using the Lower Yellow River (LYR) as prototype. Real-time observations of the water level from the micro-model were used for data assimilation. The results show that, compared to the traditional hydrodynamic model, the assimilation model could effectively update water level, flow discharge, and roughness coefficient in real time, thus yielding improved results. The mean water levels of the particle posterior distribution are closer to the observed values than before assimilation, even when water levels change greatly. In addition, the calculation results for different lead times indicate that the root mean square error of the forecasting water level gradually increases with increasing lead time. This is because the roughness value changes greatly in response to unsteady water flow, and the incurring error accumulates with the predicted period. The results show that the assimilation model can simulate water level changes in the micro-model and provide both research method and technical support for real flood forecasting in the LYR.

关键词： flood forecasting data assimilation particle filter algorithm micro-model Lower Yellow River

来源：评论

学校读者我要写书评

暂无评论

Unscented Kalman filters and particle filter Methods for Nonlinear State Estimation

引用

Procedia Technology 2014年 12卷 65-74页

作者： Katalin György András Kelemen László Dávid Department of Electrical Engineering Faculty of Technical and Human Sciences Sapientia University Tîrgu Mureş 540485 România

For nonlinear state space models to resolve the state estimation problem is difficult or these problems usually do not admit analytic solution. The Extended Kalman filter (EKF) algorithm is the widely used method for solving nonlinear state estimation applications. This method applies the standard linear Kalman filter algorithm with linearization of the nonlinear system. This algorithm requires that the process and observation noises are Gaussian distributed. The Unscented Kalman filter (UKF) is a derivative-free alternative method, and it is using one statistical linearization technique. The particle filter (PF) methods are recursive implementations of Monte-Carlo based statistical signal processing. The PF algorithm does not require either of the noises to be Gaussian and the posterior probabilities are represented by a set of randomly chosen weighted samples.

关键词： nonlinear state estimation Unscented Kalman filter particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

A Nonlinear Suboptimal Fusion algorithm Weighted by Matrices Based on LMI and NARX 43

A Nonlinear Suboptimal Fusion Algorithm Weighted by Matrices...

引用

43rd Chinese Control Conference (CCC)

作者： Guo, Hangyan Hao, Gang Heilongjiang Univ Elect Engn Inst Harbin 150080 Peoples R China Key Lab Informat Fus Estimat & Detect Harbin 150080 Peoples R China

ISBN: (纸本)9798350366907;9789887581581

In order to solve the fusion estimation problem of multi-sensor with unknown cross-covariance, an improved suboptimal fusion algorithm weighted by matrices is proposed for nonlinear systems. Firstly, for significance of linear minimum variance, the simplest constraints based on fusion weighted by matrices are derived by Shure complement theorem. These constraints can ensure the positive definiteness of the fusion estimate error covariance, and the consistency of the proposed suboptimal fusion estimation. Further, a suboptimal fusion estimation weighted by matrices is proposed based on linear matrix inequality (LMI). Considering the time-consuming problem in the optimization process of LMI algorithm and the complexity of the nonlinear system, the optimal value is obtained by the nonlinear auto-regressive neural network with exogenous input (NARX). Finally, a nonlinear suboptimal fusion algorithm weighted by matrices based on LMI and NARX is proposed in combination with the particle filter algorithm (PF).

关键词： Suboptimal fusion algorithm weighted by matrices linear matrix inequality particle filter algorithm nonlinear auto-regressive neural network with exogenous input (NARX)

来源：评论

学校读者我要写书评

暂无评论

Poster: A Magnetic Fingerprint-based Automobile Position Tracking using Smartphones 14

Poster: A Magnetic Fingerprint-based Automobile Position Tra...

引用

14th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys)

作者： Jeon, Sanghoon Lee, Haengju Son, Sang Hyuk DGIST Informat & Commun Engn Daegu South Korea

ISBN: (纸本)9781450344166

The state-of-the-art navigation frequently fails to provide precise outdoor localization especially in urban areas due to GPS errors. Conventional approaches tracking vehicle positions have used the particle filter algorithm, and we focus on magnetic fingerprint features for increasing performance of the algorithm as landmarks. We investigated the magnetic features in two conditions such as in-vehicle and at an intersection. More diverse traffic environments and an effective design of the particle filter algorithm will be complemented in the future research. We expect these magnetic fingerprints significantly improve outdoor localization algorithms especially in urban areas.

关键词： automobile localization magnetic fingerprint particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

Dynamic Human Tracking for Mobile Robot 37

Dynamic Human Tracking for Mobile Robot

引用

37th Chinese Control Conference (CCC)

作者： Su, Li Zhu, Wei Wang, Boyu Harbin Engn Univ Coll Automat Harbin 150001 Heilongjiang Peoples R China

ISBN: (纸本)9789881563958

The movement of the robot adds great difficulty to dynamic human tracking. The traditional method of image stabilization can not remove the error caused by the movement of the human body to the stable image, resulting in low tracking accuracy and low real-time performance. This paper improves on the basis of traditional image stabilization techniques. In this paper, the least squares method is used to fit the position of the human body in the first N frames to infer the position of the human body in the (N + 1)th frame. Subsequently, this paper adopts the method of sub-regional gray projection to separate the positions of the human body in two adjacent frames of images and stabilize the images, which greatly reduces the error caused by the movement of the human body on the stable image distance. In addition, the traditional mobile body tracking method cannot solve the occlusion tracking situation of the target human body while satisfying the real-time performance. In this paper, various strategies such as camshift algorithm, particle filtering method, image stabilization, and cross-frame difference are integrated, and a dynamic evaluation strategy of tracking quality is designed. The strategy can realize the normal tracking of the moving human body in the state of dynamic robot and tracking of the target human body in the occlusion situation.

关键词： Dynamic background Target tracking Background compensation Camshift algorithm particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

Research of STF-CPF-SLAM algorithm for Indoor Space Detection Mobile Robot 7

Research of STF-CPF-SLAM algorithm for Indoor Space Detectio...

引用

7th International Conference on Electronic Information Technology and Computer Engineering (EITCE)

作者： Xian, Ning Li, Danyi Shenyang Jianzhu Univ Sch Design & Art Shenyang Peoples R China

ISBN: (纸本)9798400708305

Aiming at the problem of indoor space detection mobile robots using particle filter SLAM algorithm, which may experience poor system stability and particle degeneracy after multiple iterations and updates, this paper proposes a Strong Tracking Cubature particle filter SLAM algorithm (STF-CPF-SLAM). Firstly, the Cubature Kalman (CKF) algorithm are used as the importance sampling functions of the particle filter algorithm (PF) to generate the mean and covariance distributions, simultaneously utilizing the fading factor of the Strong Tracking algorithm (STF) to compensate the system and enhance its robustness;Then, Strong Tracking Cubature particle filter algorithm is used to filter and fuse the observation data with the system model to obtain the optimized pose data of the mobile robot, thereby constructing a more accurate indoor space map;Finally, the effectiveness of the algorithm was verified through a mobile robot simulation platform. The simulation results show that the proposed algorithm reduces the error of simultaneous localization and mapping by 55.7% compared to traditional particle filter algorithms, verifying the feasibility and effectiveness of the algorithm, and improving the accuracy of indoor space exploration mobile robots in map construction. This algorithm provides a new reference for simultaneous localization and mapping of mobile robots.

关键词： Simultaneous Localization and Mapping (SLAM) Indoor Mobile Robot particle filter algorithm Strong Tracking filter

来源：评论

学校读者我要写书评

暂无评论

Research on the kinematic parameter calibration method of industrial robot based on LM and PF algorithm 32

Research on the kinematic parameter calibration method of in...

引用

32nd Chinese Control And Decision Conference (CCDC)

作者： Deng, Xin Ge, Lianzheng Li, Ruifeng Liu, Zhiheng Harbin Inst Technol Harbin 150001 Peoples R China

ISBN: (纸本)9781728158556

The absolute positioning accuracy of the industrial robot is one of its important performance indexes, which is impacted by the key factor of robotic kinematic parameters. Therefore, based on the MDH model a calibration method of robot kinematic parameters, which combines the Levenberg-Marquardt algorithm with the particle filter algorithm is proposed. Firstly, the MDH model of an industrial robot is established, and the parameters in the tool coordinate transformation are also regarded as the parameters to be calibrated. Then the end error model is established. Secondly, the initial optimization is carried out using the Levenberg-Marquardt (LM) algorithm. Meanwhile, the particle filter algorithm is used to further optimize the parameters considering the measurement error. Finally, compared with other methods, such as spatial circle fitting method, least square method and extended Kalman filter algorithm. The results show that the kinematic parameters of the robot are accurately calibrated and the absolute positioning accuracy of the industrial robot is significantly improved by this method. Compared with other methods, the parameters calibrated by this method have stronger generalization ability.

关键词： Kinematic parameters MDH model Levenberg-Marquardt algorithm particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

Efficient Bus Arrival Time Prediction Based on Spark Streaming Platform 23

Efficient Bus Arrival Time Prediction Based on Spark Streami...

引用

IEEE 23rd International Conference on Computer Supported Cooperative Work in Design (CSCWD)

作者： Liu, Jing Xiao, Guanfeng Inner Mongolia Univ Hohhot Peoples R China

ISBN: (纸本)9781728103501

In smart city development, the prediction of bus arrival time is a popular research issue, which often uses GPS data and other related bus data to conduct collaborative data analysis. It is of great importance for improving the public transportation services. But the accuracy and the efficiency of bus arrival time prediction is still the major obstacles. In this paper, an optimized particle-filtering algorithm is used to establish a bus arrival time prediction model. To better solve the problem of prediction error and particle optimization in the process of using particle filter algorithms, the prediction model is improved by introducing the latest bus speed for collaborative data analysis, which improves the accuracy of the bus arrival time prediction based on the actual road conditions and can simultaneously predict the arrival time of multiple buses. Based on the above model and the Spark streaming platform, a real-time bus arrival time prediction software system is implemented. The experimental results show that our proposed model and system can accurately predict the bus arrival time and then well promote the bus travel experience for citizens.

关键词： Bus arrival time prediction particle filter algorithm Spark streaming smart city

来源：评论

学校读者我要写书评

暂无评论

Option pricing under stock market cycles with jump risks: evidence from the S&P 500 index

引用

REVIEW OF QUANTITATIVE FINANCE AND ACCOUNTING 2021年第1期56卷 25-51页

作者： Wang, Shin-Yun Chuang, Ming-Che Lin, Shih-Kuei Shyu, So-De Natl Dong Hwa Univ Dept Finance Hualien Taiwan Feng Chia Univ Dept Finance Taichung Taiwan Natl Chengchi Univ Coll Commerce Dept Money & Banking 64Sec 2ZhiNan Rd Taipei 11605 Taiwan Natl Chengchi Univ Coll Commerce Risk & Insurance Res Ctr 64Sec 2ZhiNan Rd Taipei 11605 Taiwan Takming Univ Sci & Technol Dept Accounting Informat Taipei Taiwan

This study incorporates the Markov switching model with return jumps to depict the behavior of stock returns. Based on the daily Standard & Poor's 500 index (hereafter SPX) and the daily closing price of the call option, we use the particle filtering algorithm to fit the parameter of the model. The joint log-likelihood evaluates the model performance: the weighted average log-likelihood with the rate of return of the SPX and the relative implied volatility root-mean-squared error for the SPX call options. The empirical results identify that the pricing model with jump risks improves the pricing performance to the median-term call options. According to the sensitivity analysis, option prices increase with the probability of remaining in the recession state but decrease with the probability of remaining in the expansion state. Moreover, the call option prices are positively associated with the volatility in each market state and the factors of jump risk.

关键词： Markov switching Jump risks Volatility smile particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：